ci: backport LLM container pipeline to release 1.3.1#1823
Open
kcywinski0 wants to merge 7 commits into
Open
Conversation
Adds a new Jenkins matrix pipeline that builds the three NIXL inference container variants (vllm-nixl, sglang-nixl, sglang-cu13-nixl) from a published NIXL wheel set, for x86_64 and aarch64, and publishes multi-arch manifests. Mirrors the manual procedure documented at README.md so that release-candidate inference images can be cut without running the build steps by hand. Uses native podman for build/push/manifest operations (no docker on the build pod). Cross-arch aarch64 builds run on x86_64 hosts via QEMU. Signed-off-by: Iaroslav Sydoruk <isydoruk@nvidia.com>
Signed-off-by: Iaroslav Sydoruk <isydoruk@nvidia.com>
TinyLlama/TinyLlama-1.1B-Chat-v1.0 (~550MB) — smoke/perf for both vllm and sglang Qwen/Qwen3-8B (~16GB) — accuracy tests for sglang only (vllm accuracy is a no-op) Signed-off-by: Iaroslav Sydoruk <isydoruk@nvidia.com>
|
👋 Hi kcywinski0! Thank you for contributing to ai-dynamo/nixl. Your PR reviewers will review your contribution then trigger the CI to test your changes. 🚀 |
Replace the deprecated huggingface-cli invocation so LLM container builds can prefetch models with current Hugging Face images.
Use huggingface_hub.snapshot_download directly so LLM container builds do not depend on deprecated or missing Hugging Face CLI entrypoints.
Install or upgrade huggingface_hub before prefetching LLM test models so container builds do not depend on base image contents.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Test plan
.ci/jenkins/lib/build-llm-container-matrix.yaml.